# Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

arXiv: https://arxiv.org/abs/2606.00558 · HTML: https://mlsanity.com/paper/2606.00558/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 67 references that are in the map.
- First posted on arXiv 30 May 2026.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations](https://mlsanity.com/paper/2003.12237/) (2020)
- [Learning to See by Looking at Noise](https://mlsanity.com/paper/2106.05963/) (2021)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2010.04647/) (2020)
- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2206.02465/) (2022)
- [Prompt-based Distribution Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2312.09553/) (2023)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Positive-incentive Noise](https://mlsanity.com/paper/2212.09541/) (2022)
- [Enhance Vision-Language Alignment with Noise](https://mlsanity.com/paper/2412.10817/) (2024)
- [Rethinking Propagation for Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2402.05660/) (2024)
- [Heterogeneous Domain Adaptation via Soft Transfer Network](https://mlsanity.com/paper/1908.10552/) (2019)
- [A Recent Survey of Heterogeneous Transfer Learning](https://mlsanity.com/paper/2310.08459/) (2023)
- [M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Training](https://mlsanity.com/paper/2404.17391/) (2024)
- [Towards Unsupervised Domain Adaptation via Domain-Transformer](https://mlsanity.com/paper/2202.13777/) (2022)
- [Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning](https://mlsanity.com/paper/2410.11206/) (2024)

## Abstract (arXiv)

Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain. The source domain typically contains semantically meaningful samples (*e.g.*, images) to facilitate effective knowledge transfer. However, a recent study observes that the noise domain constructed from simple distributions (*e.g.*, Gaussian distributions) can serve as a surrogate source domain in the semi-supervised setting, where only a small proportion of target samples are labeled while most remain unlabeled. Based on this surprising observation, we formulate a novel problem termed *Semi-Supervised Noise Adaptation* (SSNA), which aims to leverage a synthetic noise domain to improve the generalization of the target domain. To address this problem, we first establish a generalization bound characterizing the effect of the noise domain on generalization, based on which we propose a Noise Adaptation Framework (NAF). Extensive experiments demonstrate that NAF effectively leverages the noise domain to tighten the generalization bound of the target domain, leading to improved performance. The codes are available at https://github.com/AIResearch-Group/SSNA.